© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137151
    Prev
    Next
    INDEX
    Explanations

    Too much

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    гай
    0.41
    REQ
    0.38
    getpath
    0.38
     свойства
    0.38
     운동
    0.38
     пен
    0.37
     вла
    0.37
     wet
    0.37
    湿
    0.36
    ਵੇਂ
    0.35
    POSITIVE LOGITS
     over
    0.52
    over
    0.45
     Over
    0.44
     discrete
    0.42
    optimization
    0.42
    discrete
    0.41
    Distribution
    0.41
    Over
    0.40
    distribution
    0.40
     SCORE
    0.39
    Activations Density 0.009%

    No Known Activations